diff --git a/Fine_tune_LLMs_with_Axolotl.ipynb b/Fine_tune_LLMs_with_Axolotl.ipynb
new file mode 100644
index 0000000..edc6e0c
--- /dev/null
+++ b/Fine_tune_LLMs_with_Axolotl.ipynb
@@ -0,0 +1,1555 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "view-in-github",
+        "colab_type": "text"
+      },
+      "source": [
+        "<a href=\"https://colab.research.google.com/github/mlabonne/llm-course/blob/main/Fine_tune_LLMs_with_Axolotl.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# Fine-tune LLMs with Axolotl\n",
+        "\n",
+        "> 🗣️ [Large Language Model Course](https://github.com/mlabonne/llm-course)\n",
+        "\n",
+        "❤️ Created by [@maximelabonne](https://twitter.com/maximelabonne), based on [Giorgio](https://github.com/g-i-o-r-g-i-o)'s notebook and Axolotl's [example](https://github.com/OpenAccess-AI-Collective/axolotl/blob/main/examples/colab-notebooks/colab-axolotl-example.ipynb)."
+      ],
+      "metadata": {
+        "id": "mL-BPZyZ0gtV"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "!git clone -q https://github.com/OpenAccess-AI-Collective/axolotl\n",
+        "%cd axolotl\n",
+        "!pip install -qqq packaging huggingface_hub --progress-bar off\n",
+        "!pip install -qqq -e '.[flash-attn,deepspeed]' --progress-bar off"
+      ],
+      "metadata": {
+        "id": "BI6B0Bfe0hxr"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "import yaml\n",
+        "\n",
+        "new_model = \"mlabonne/TinyAlpaca\"\n",
+        "yaml_string = \"\"\"\n",
+        "base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T\n",
+        "model_type: LlamaForCausalLM\n",
+        "tokenizer_type: LlamaTokenizer\n",
+        "is_llama_derived_model: true\n",
+        "\n",
+        "load_in_8bit: false\n",
+        "load_in_4bit: true\n",
+        "strict: false\n",
+        "\n",
+        "datasets:\n",
+        "  - path: mhenrichsen/alpaca_2k_test\n",
+        "    type: alpaca\n",
+        "dataset_prepared_path:\n",
+        "val_set_size: 0.05\n",
+        "output_dir: ./qlora-out\n",
+        "\n",
+        "adapter: qlora\n",
+        "lora_model_dir:\n",
+        "\n",
+        "sequence_len: 1096\n",
+        "sample_packing: true\n",
+        "pad_to_sequence_len: true\n",
+        "\n",
+        "lora_r: 32\n",
+        "lora_alpha: 16\n",
+        "lora_dropout: 0.05\n",
+        "lora_target_modules:\n",
+        "lora_target_linear: true\n",
+        "lora_fan_in_fan_out:\n",
+        "\n",
+        "wandb_project:\n",
+        "wandb_entity:\n",
+        "wandb_watch:\n",
+        "wandb_name:\n",
+        "wandb_log_model:\n",
+        "\n",
+        "mlflow_experiment_name: colab-example\n",
+        "\n",
+        "gradient_accumulation_steps: 1\n",
+        "micro_batch_size: 1\n",
+        "num_epochs: 4\n",
+        "max_steps: 20\n",
+        "optimizer: paged_adamw_32bit\n",
+        "lr_scheduler: cosine\n",
+        "learning_rate: 0.0002\n",
+        "\n",
+        "train_on_inputs: false\n",
+        "group_by_length: false\n",
+        "bf16: false\n",
+        "fp16: true\n",
+        "tf32: false\n",
+        "\n",
+        "gradient_checkpointing: true\n",
+        "early_stopping_patience:\n",
+        "resume_from_checkpoint:\n",
+        "local_rank:\n",
+        "logging_steps: 1\n",
+        "xformers_attention:\n",
+        "flash_attention: false\n",
+        "\n",
+        "warmup_steps: 10\n",
+        "evals_per_epoch:\n",
+        "saves_per_epoch:\n",
+        "debug:\n",
+        "deepspeed:\n",
+        "weight_decay: 0.0\n",
+        "fsdp:\n",
+        "fsdp_config:\n",
+        "special_tokens:\n",
+        "\n",
+        "\"\"\"\n",
+        "\n",
+        "# Convert the YAML string to a Python dictionary\n",
+        "yaml_dict = yaml.safe_load(yaml_string)\n",
+        "\n",
+        "# Specify your file path\n",
+        "yaml_file = 'config.yaml'\n",
+        "\n",
+        "# Write the YAML file\n",
+        "with open(yaml_file, 'w') as file:\n",
+        "    yaml.dump(yaml_dict, file)"
+      ],
+      "metadata": {
+        "id": "70zJf1hi0huQ"
+      },
+      "execution_count": 5,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 6,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "ffcc0IB9Sr-z",
+        "outputId": "f64291b0-0867-440b-b7b9-683fa66e3a08"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "The following values were not passed to `accelerate launch` and had defaults used instead:\n",
+            "\t`--num_processes` was set to a value of `1`\n",
+            "\t`--num_machines` was set to a value of `1`\n",
+            "\t`--mixed_precision` was set to a value of `'no'`\n",
+            "\t`--dynamo_backend` was set to a value of `'no'`\n",
+            "To avoid this warning pass in values for each of the problematic parameters or run `accelerate config`.\n",
+            "2024-01-27 22:05:58.426793: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n",
+            "2024-01-27 22:05:58.426851: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n",
+            "2024-01-27 22:05:58.428152: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n",
+            "2024-01-27 22:05:59.454203: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT\n",
+            "[2024-01-27 22:06:00,824] [INFO] [datasets.<module>:58] [PID:2797] PyTorch version 2.1.2 available.\n",
+            "[2024-01-27 22:06:00,825] [INFO] [datasets.<module>:95] [PID:2797] TensorFlow version 2.15.0 available.\n",
+            "[2024-01-27 22:06:00,827] [INFO] [datasets.<module>:108] [PID:2797] JAX version 0.4.23 available.\n",
+            "[2024-01-27 22:06:01,844] [INFO] [real_accelerator.py:191:get_accelerator] Setting ds_accelerator to cuda (auto detect)\n",
+            "config.json: 100% 560/560 [00:00<00:00, 3.84MB/s]\n",
+            "[2024-01-27 22:06:03,638] [INFO] [axolotl.normalize_config:170] [PID:2797] [RANK:0] GPU memory usage baseline: 0.000GB (+0.255GB misc)\u001b[39m\n",
+            "                                 dP            dP   dP \n",
+            "                                 88            88   88 \n",
+            "      .d8888b. dP.  .dP .d8888b. 88 .d8888b. d8888P 88 \n",
+            "      88'  `88  `8bd8'  88'  `88 88 88'  `88   88   88 \n",
+            "      88.  .88  .d88b.  88.  .88 88 88.  .88   88   88 \n",
+            "      `88888P8 dP'  `dP `88888P' dP `88888P'   dP   dP \n",
+            "                                                       \n",
+            "                                                       \n",
+            "\n",
+            "\u001b[33m[2024-01-27 22:06:03,642] [WARNING] [axolotl.scripts.check_user_token:382] [PID:2797] [RANK:0] Error verifying HuggingFace token. Remember to log in using `huggingface-cli login` and get your access token from https://huggingface.co/settings/tokens if you want to use gated models or datasets.\u001b[39m\n",
+            "tokenizer_config.json: 100% 776/776 [00:00<00:00, 4.70MB/s]\n",
+            "tokenizer.model: 100% 500k/500k [00:00<00:00, 1.77MB/s]\n",
+            "special_tokens_map.json: 100% 414/414 [00:00<00:00, 1.73MB/s]\n",
+            "tokenizer.json: 100% 1.84M/1.84M [00:00<00:00, 4.52MB/s]\n",
+            "[2024-01-27 22:06:05,850] [DEBUG] [axolotl.load_tokenizer:216] [PID:2797] [RANK:0] EOS: 2 / </s>\u001b[39m\n",
+            "[2024-01-27 22:06:05,850] [DEBUG] [axolotl.load_tokenizer:217] [PID:2797] [RANK:0] BOS: 1 / <s>\u001b[39m\n",
+            "[2024-01-27 22:06:05,850] [DEBUG] [axolotl.load_tokenizer:218] [PID:2797] [RANK:0] PAD: 2 / </s>\u001b[39m\n",
+            "[2024-01-27 22:06:05,850] [DEBUG] [axolotl.load_tokenizer:219] [PID:2797] [RANK:0] UNK: 0 / <unk>\u001b[39m\n",
+            "[2024-01-27 22:06:05,850] [INFO] [axolotl.load_tokenizer:230] [PID:2797] [RANK:0] No Chat template selected. Consider adding a chat template for easier inference.\u001b[39m\n",
+            "[2024-01-27 22:06:05,850] [INFO] [axolotl.load_tokenized_prepared_datasets:182] [PID:2797] [RANK:0] Unable to find prepared dataset in last_run_prepared/c0112363192ff19da1e486577d4bf28b\u001b[39m\n",
+            "[2024-01-27 22:06:05,850] [INFO] [axolotl.load_tokenized_prepared_datasets:183] [PID:2797] [RANK:0] Loading raw datasets...\u001b[39m\n",
+            "\u001b[33m[2024-01-27 22:06:05,850] [WARNING] [axolotl.load_tokenized_prepared_datasets:185] [PID:2797] [RANK:0] Processing datasets during training can lead to VRAM instability. Please pre-process your dataset.\u001b[39m\n",
+            "[2024-01-27 22:06:05,850] [INFO] [axolotl.load_tokenized_prepared_datasets:192] [PID:2797] [RANK:0] No seed provided, using default seed of 42\u001b[39m\n",
+            "Downloading readme: 100% 28.0/28.0 [00:00<00:00, 219kB/s]\n",
+            "Downloading data: 100% 1.76M/1.76M [00:00<00:00, 2.45MB/s]\n",
+            "Generating train split: 2000 examples [00:00, 37778.35 examples/s]\n",
+            "Tokenizing Prompts (num_proc=2): 100% 2000/2000 [00:05<00:00, 352.09 examples/s]\n",
+            "[2024-01-27 22:06:17,586] [INFO] [axolotl.load_tokenized_prepared_datasets:395] [PID:2797] [RANK:0] merging datasets\u001b[39m\n",
+            "Dropping Long Sequences (num_proc=2): 100% 2000/2000 [00:00<00:00, 2927.43 examples/s]\n",
+            "Add position_id column (Sample Packing) (num_proc=2): 100% 2000/2000 [00:00<00:00, 3089.00 examples/s]\n",
+            "[2024-01-27 22:06:19,041] [INFO] [axolotl.load_tokenized_prepared_datasets:405] [PID:2797] [RANK:0] Saving merged prepared dataset to disk... last_run_prepared/c0112363192ff19da1e486577d4bf28b\u001b[39m\n",
+            "Saving the dataset (1/1 shards): 100% 2000/2000 [00:00<00:00, 142755.66 examples/s]\n",
+            "[2024-01-27 22:06:19,067] [DEBUG] [axolotl.log:61] [PID:2797] [RANK:0] total_num_tokens: 22777\u001b[39m\n",
+            "[2024-01-27 22:06:19,069] [DEBUG] [axolotl.log:61] [PID:2797] [RANK:0] `total_supervised_tokens: 16719`\u001b[39m\n",
+            "[2024-01-27 22:06:24,965] [INFO] [axolotl.utils.samplers.multipack._len_est:178] [PID:2797] [RANK:0] packing_efficiency_estimate: 1.0 total_num_tokens per device: 22777\u001b[39m\n",
+            "[2024-01-27 22:06:24,965] [DEBUG] [axolotl.log:61] [PID:2797] [RANK:0] data_loader_len: 19\u001b[39m\n",
+            "[2024-01-27 22:06:24,966] [INFO] [axolotl.log:61] [PID:2797] [RANK:0] sample_packing_eff_est across ranks: [0.8659139294403893]\u001b[39m\n",
+            "[2024-01-27 22:06:24,966] [DEBUG] [axolotl.log:61] [PID:2797] [RANK:0] sample_packing_eff_est: None\u001b[39m\n",
+            "[2024-01-27 22:06:24,966] [DEBUG] [axolotl.log:61] [PID:2797] [RANK:0] total_num_steps: 76\u001b[39m\n",
+            "[2024-01-27 22:06:24,970] [DEBUG] [axolotl.log:61] [PID:2797] [RANK:0] total_num_tokens: 414041\u001b[39m\n",
+            "[2024-01-27 22:06:25,001] [DEBUG] [axolotl.log:61] [PID:2797] [RANK:0] `total_supervised_tokens: 294246`\u001b[39m\n",
+            "[2024-01-27 22:06:25,009] [INFO] [axolotl.utils.samplers.multipack._len_est:178] [PID:2797] [RANK:0] packing_efficiency_estimate: 1.0 total_num_tokens per device: 414041\u001b[39m\n",
+            "[2024-01-27 22:06:25,009] [DEBUG] [axolotl.log:61] [PID:2797] [RANK:0] data_loader_len: 372\u001b[39m\n",
+            "[2024-01-27 22:06:25,009] [INFO] [axolotl.log:61] [PID:2797] [RANK:0] sample_packing_eff_est across ranks: [0.8624991667499917]\u001b[39m\n",
+            "[2024-01-27 22:06:25,009] [DEBUG] [axolotl.log:61] [PID:2797] [RANK:0] sample_packing_eff_est: 0.87\u001b[39m\n",
+            "[2024-01-27 22:06:25,009] [DEBUG] [axolotl.log:61] [PID:2797] [RANK:0] total_num_steps: 1488\u001b[39m\n",
+            "[2024-01-27 22:06:25,009] [INFO] [axolotl.prepare_dataset:115] [PID:2797] [RANK:0] Maximum number of steps set at 20\u001b[39m\n",
+            "[2024-01-27 22:06:25,010] [DEBUG] [axolotl.train.log:61] [PID:2797] [RANK:0] loading tokenizer... TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T\u001b[39m\n",
+            "[2024-01-27 22:06:25,574] [DEBUG] [axolotl.load_tokenizer:216] [PID:2797] [RANK:0] EOS: 2 / </s>\u001b[39m\n",
+            "[2024-01-27 22:06:25,575] [DEBUG] [axolotl.load_tokenizer:217] [PID:2797] [RANK:0] BOS: 1 / <s>\u001b[39m\n",
+            "[2024-01-27 22:06:25,575] [DEBUG] [axolotl.load_tokenizer:218] [PID:2797] [RANK:0] PAD: 2 / </s>\u001b[39m\n",
+            "[2024-01-27 22:06:25,575] [DEBUG] [axolotl.load_tokenizer:219] [PID:2797] [RANK:0] UNK: 0 / <unk>\u001b[39m\n",
+            "[2024-01-27 22:06:25,575] [INFO] [axolotl.load_tokenizer:230] [PID:2797] [RANK:0] No Chat template selected. Consider adding a chat template for easier inference.\u001b[39m\n",
+            "[2024-01-27 22:06:25,575] [DEBUG] [axolotl.train.log:61] [PID:2797] [RANK:0] loading model and peft_config...\u001b[39m\n",
+            "[2024-01-27 22:06:25,678] [INFO] [axolotl.load_model:372] [PID:2797] [RANK:0] patching _expand_mask\u001b[39m\n",
+            "model.safetensors: 100% 4.40G/4.40G [01:42<00:00, 42.8MB/s]\n",
+            "generation_config.json: 100% 129/129 [00:00<00:00, 758kB/s]\n",
+            "[2024-01-27 22:08:13,799] [INFO] [axolotl.load_model:641] [PID:2797] [RANK:0] GPU memory usage after model load: 0.753GB (+0.022GB cache, +0.368GB misc)\u001b[39m\n",
+            "[2024-01-27 22:08:13,825] [INFO] [axolotl.load_model:673] [PID:2797] [RANK:0] converting PEFT model w/ prepare_model_for_kbit_training\u001b[39m\n",
+            "[2024-01-27 22:08:13,829] [INFO] [axolotl.load_model:685] [PID:2797] [RANK:0] converting modules to torch.float16 for flash attention\u001b[39m\n",
+            "[2024-01-27 22:08:13,832] [INFO] [axolotl.load_lora:797] [PID:2797] [RANK:0] found linear modules: ['v_proj', 'k_proj', 'gate_proj', 'up_proj', 'o_proj', 'q_proj', 'down_proj']\u001b[39m\n",
+            "trainable params: 25,231,360 || all params: 1,125,279,744 || trainable%: 2.2422299996542017\n",
+            "[2024-01-27 22:08:14,263] [INFO] [axolotl.load_model:722] [PID:2797] [RANK:0] GPU memory usage after adapters: 0.847GB (+0.514GB cache, +0.368GB misc)\u001b[39m\n",
+            "[2024-01-27 22:08:14,273] [INFO] [axolotl.train.log:61] [PID:2797] [RANK:0] Pre-saving adapter config to ./qlora-out\u001b[39m\n",
+            "[2024-01-27 22:08:14,280] [INFO] [axolotl.train.log:61] [PID:2797] [RANK:0] Starting trainer...\u001b[39m\n",
+            "[2024-01-27 22:08:14,686] [INFO] [axolotl.utils.samplers.multipack._len_est:178] [PID:2797] [RANK:0] packing_efficiency_estimate: 0.87 total_num_tokens per device: 414041\u001b[39m\n",
+            "[2024-01-27 22:08:14,688] [INFO] [axolotl.utils.samplers.multipack._len_est:178] [PID:2797] [RANK:0] packing_efficiency_estimate: 0.87 total_num_tokens per device: 414041\u001b[39m\n",
+            "[2024-01-27 22:08:14,850] [INFO] [axolotl.callbacks.on_train_begin:601] [PID:2797] [RANK:0] The Axolotl config has been saved to the MLflow artifacts.\u001b[39m\n",
+            "  0% 0/20 [00:00<?, ?it/s][2024-01-27 22:08:14,853] [INFO] [axolotl.utils.samplers.multipack._len_est:178] [PID:2797] [RANK:0] packing_efficiency_estimate: 0.87 total_num_tokens per device: 414041\u001b[39m\n",
+            "{'loss': 1.6463, 'learning_rate': 2e-05, 'epoch': 0.0}\n",
+            "  5% 1/20 [00:02<00:45,  2.41s/it][2024-01-27 22:08:18,019] [INFO] [axolotl.callbacks.on_step_end:125] [PID:2797] [RANK:0] GPU memory usage while training: 0.963GB (+0.805GB cache, +0.638GB misc)\u001b[39m\n",
+            "{'loss': 4.8805, 'learning_rate': 4e-05, 'epoch': 0.0}\n",
+            "{'loss': 4.4957, 'learning_rate': 6e-05, 'epoch': 0.01}\n",
+            "{'loss': 4.4627, 'learning_rate': 8e-05, 'epoch': 0.01}\n",
+            "{'loss': 4.8849, 'learning_rate': 0.0001, 'epoch': 0.01}\n",
+            "{'loss': 5.0871, 'learning_rate': 0.00012, 'epoch': 0.01}\n",
+            "{'loss': 3.0099, 'learning_rate': 0.00014, 'epoch': 0.02}\n",
+            "{'loss': 4.4522, 'learning_rate': 0.00016, 'epoch': 0.02}\n",
+            "{'loss': 2.2085, 'learning_rate': 0.00018, 'epoch': 0.02}\n",
+            "{'loss': 4.4377, 'learning_rate': 0.0002, 'epoch': 0.02}\n",
+            "{'loss': 3.7593, 'learning_rate': 0.00019510565162951537, 'epoch': 0.03}\n",
+            "{'loss': 3.5486, 'learning_rate': 0.00018090169943749476, 'epoch': 0.03}\n",
+            "{'loss': 3.7615, 'learning_rate': 0.00015877852522924732, 'epoch': 0.03}\n",
+            "{'loss': 3.5778, 'learning_rate': 0.00013090169943749476, 'epoch': 0.03}\n",
+            "{'loss': 3.3562, 'learning_rate': 0.0001, 'epoch': 0.04}\n",
+            "{'loss': 3.7881, 'learning_rate': 6.909830056250527e-05, 'epoch': 0.04}\n",
+            "{'loss': 3.4147, 'learning_rate': 4.12214747707527e-05, 'epoch': 0.04}\n",
+            "{'loss': 3.7467, 'learning_rate': 1.9098300562505266e-05, 'epoch': 0.04}\n",
+            "{'loss': 3.6867, 'learning_rate': 4.8943483704846475e-06, 'epoch': 0.04}\n",
+            "{'loss': 4.0308, 'learning_rate': 0.0, 'epoch': 0.05}\n",
+            "100% 20/20 [00:17<00:00,  1.26it/s][2024-01-27 22:08:32,098] [INFO] [axolotl.utils.samplers.multipack._len_est:178] [PID:2797] [RANK:0] packing_efficiency_estimate: 0.87 total_num_tokens per device: 22777\u001b[39m\n",
+            "[2024-01-27 22:08:32,232] [INFO] [axolotl.utils.samplers.multipack._len_est:178] [PID:2797] [RANK:0] packing_efficiency_estimate: 0.87 total_num_tokens per device: 22777\u001b[39m\n",
+            "[2024-01-27 22:08:32,232] [INFO] [axolotl.utils.samplers.multipack._len_est:178] [PID:2797] [RANK:0] packing_efficiency_estimate: 0.87 total_num_tokens per device: 22777\u001b[39m\n",
+            "\n",
+            "  0% 0/22 [00:00<?, ?it/s]\u001b[A[2024-01-27 22:08:32,451] [INFO] [axolotl.utils.samplers.multipack._len_est:178] [PID:2797] [RANK:0] packing_efficiency_estimate: 0.87 total_num_tokens per device: 22777\u001b[39m\n",
+            "\n",
+            "  9% 2/22 [00:00<00:02,  9.16it/s]\u001b[A[2024-01-27 22:08:32,669] [INFO] [axolotl.utils.samplers.multipack._len_est:178] [PID:2797] [RANK:0] packing_efficiency_estimate: 0.87 total_num_tokens per device: 22777\u001b[39m\n",
+            "\n",
+            " 14% 3/22 [00:00<00:02,  6.46it/s]\u001b[A[2024-01-27 22:08:32,890] [INFO] [axolotl.utils.samplers.multipack._len_est:178] [PID:2797] [RANK:0] packing_efficiency_estimate: 0.87 total_num_tokens per device: 22777\u001b[39m\n",
+            "\n",
+            " 18% 4/22 [00:00<00:03,  5.58it/s]\u001b[A[2024-01-27 22:08:33,119] [INFO] [axolotl.utils.samplers.multipack._len_est:178] [PID:2797] [RANK:0] packing_efficiency_estimate: 0.87 total_num_tokens per device: 22777\u001b[39m\n",
+            "\n",
+            " 23% 5/22 [00:00<00:03,  5.08it/s]\u001b[A[2024-01-27 22:08:33,339] [INFO] [axolotl.utils.samplers.multipack._len_est:178] [PID:2797] [RANK:0] packing_efficiency_estimate: 0.87 total_num_tokens per device: 22777\u001b[39m\n",
+            "\n",
+            " 27% 6/22 [00:01<00:03,  4.89it/s]\u001b[A[2024-01-27 22:08:33,559] [INFO] [axolotl.utils.samplers.multipack._len_est:178] [PID:2797] [RANK:0] packing_efficiency_estimate: 0.87 total_num_tokens per device: 22777\u001b[39m\n",
+            "\n",
+            " 32% 7/22 [00:01<00:03,  4.78it/s]\u001b[A[2024-01-27 22:08:33,779] [INFO] [axolotl.utils.samplers.multipack._len_est:178] [PID:2797] [RANK:0] packing_efficiency_estimate: 0.87 total_num_tokens per device: 22777\u001b[39m\n",
+            "\n",
+            " 36% 8/22 [00:01<00:02,  4.70it/s]\u001b[A[2024-01-27 22:08:34,004] [INFO] [axolotl.utils.samplers.multipack._len_est:178] [PID:2797] [RANK:0] packing_efficiency_estimate: 0.87 total_num_tokens per device: 22777\u001b[39m\n",
+            "\n",
+            " 41% 9/22 [00:01<00:02,  4.62it/s]\u001b[A[2024-01-27 22:08:34,224] [INFO] [axolotl.utils.samplers.multipack._len_est:178] [PID:2797] [RANK:0] packing_efficiency_estimate: 0.87 total_num_tokens per device: 22777\u001b[39m\n",
+            "\n",
+            " 45% 10/22 [00:01<00:02,  4.59it/s]\u001b[A[2024-01-27 22:08:34,447] [INFO] [axolotl.utils.samplers.multipack._len_est:178] [PID:2797] [RANK:0] packing_efficiency_estimate: 0.87 total_num_tokens per device: 22777\u001b[39m\n",
+            "\n",
+            " 50% 11/22 [00:02<00:02,  4.56it/s]\u001b[A[2024-01-27 22:08:34,670] [INFO] [axolotl.utils.samplers.multipack._len_est:178] [PID:2797] [RANK:0] packing_efficiency_estimate: 0.87 total_num_tokens per device: 22777\u001b[39m\n",
+            "\n",
+            " 55% 12/22 [00:02<00:02,  4.54it/s]\u001b[A[2024-01-27 22:08:34,889] [INFO] [axolotl.utils.samplers.multipack._len_est:178] [PID:2797] [RANK:0] packing_efficiency_estimate: 0.87 total_num_tokens per device: 22777\u001b[39m\n",
+            "\n",
+            " 59% 13/22 [00:02<00:01,  4.55it/s]\u001b[A[2024-01-27 22:08:35,115] [INFO] [axolotl.utils.samplers.multipack._len_est:178] [PID:2797] [RANK:0] packing_efficiency_estimate: 0.87 total_num_tokens per device: 22777\u001b[39m\n",
+            "\n",
+            " 64% 14/22 [00:02<00:01,  4.51it/s]\u001b[A[2024-01-27 22:08:35,337] [INFO] [axolotl.utils.samplers.multipack._len_est:178] [PID:2797] [RANK:0] packing_efficiency_estimate: 0.87 total_num_tokens per device: 22777\u001b[39m\n",
+            "\n",
+            " 68% 15/22 [00:03<00:01,  4.51it/s]\u001b[A[2024-01-27 22:08:35,559] [INFO] [axolotl.utils.samplers.multipack._len_est:178] [PID:2797] [RANK:0] packing_efficiency_estimate: 0.87 total_num_tokens per device: 22777\u001b[39m\n",
+            "\n",
+            " 73% 16/22 [00:03<00:01,  4.51it/s]\u001b[A[2024-01-27 22:08:35,783] [INFO] [axolotl.utils.samplers.multipack._len_est:178] [PID:2797] [RANK:0] packing_efficiency_estimate: 0.87 total_num_tokens per device: 22777\u001b[39m\n",
+            "\n",
+            " 77% 17/22 [00:03<00:01,  4.49it/s]\u001b[A[2024-01-27 22:08:36,005] [INFO] [axolotl.utils.samplers.multipack._len_est:178] [PID:2797] [RANK:0] packing_efficiency_estimate: 0.87 total_num_tokens per device: 22777\u001b[39m\n",
+            "\n",
+            " 82% 18/22 [00:03<00:00,  4.50it/s]\u001b[A[2024-01-27 22:08:36,228] [INFO] [axolotl.utils.samplers.multipack._len_est:178] [PID:2797] [RANK:0] packing_efficiency_estimate: 0.87 total_num_tokens per device: 22777\u001b[39m\n",
+            "\n",
+            " 86% 19/22 [00:03<00:00,  4.50it/s]\u001b[A[2024-01-27 22:08:36,449] [INFO] [axolotl.utils.samplers.multipack._len_est:178] [PID:2797] [RANK:0] packing_efficiency_estimate: 0.87 total_num_tokens per device: 22777\u001b[39m\n",
+            "\n",
+            " 91% 20/22 [00:04<00:00,  4.50it/s]\u001b[A[2024-01-27 22:08:36,676] [INFO] [axolotl.utils.samplers.multipack._len_est:178] [PID:2797] [RANK:0] packing_efficiency_estimate: 0.87 total_num_tokens per device: 22777\u001b[39m\n",
+            "\n",
+            " 95% 21/22 [00:04<00:00,  4.47it/s]\u001b[A[2024-01-27 22:08:36,896] [INFO] [axolotl.utils.samplers.multipack._len_est:178] [PID:2797] [RANK:0] packing_efficiency_estimate: 0.87 total_num_tokens per device: 22777\u001b[39m\n",
+            "\n",
+            "100% 22/22 [00:04<00:00,  4.50it/s]\u001b[A[2024-01-27 22:08:37,116] [INFO] [axolotl.utils.samplers.multipack._len_est:178] [PID:2797] [RANK:0] packing_efficiency_estimate: 0.87 total_num_tokens per device: 22777\u001b[39m\n",
+            "\n",
+            "23it [00:04,  4.51it/s]            \u001b[A[2024-01-27 22:08:37,336] [INFO] [axolotl.utils.samplers.multipack._len_est:178] [PID:2797] [RANK:0] packing_efficiency_estimate: 0.87 total_num_tokens per device: 22777\u001b[39m\n",
+            "\n",
+            "24it [00:05,  4.52it/s]\u001b[A[2024-01-27 22:08:37,556] [INFO] [axolotl.utils.samplers.multipack._len_est:178] [PID:2797] [RANK:0] packing_efficiency_estimate: 0.87 total_num_tokens per device: 22777\u001b[39m\n",
+            "\n",
+            "                                   \n",
+            "\u001b[A{'eval_loss': 3.513343572616577, 'eval_runtime': 5.5482, 'eval_samples_per_second': 18.024, 'eval_steps_per_second': 18.024, 'epoch': 0.05}\n",
+            "100% 20/20 [00:22<00:00,  1.26it/s]\n",
+            "25it [00:05,  4.53it/s]\u001b[A\n",
+            "{'train_runtime': 24.8459, 'train_samples_per_second': 0.805, 'train_steps_per_second': 0.805, 'train_loss': 3.8117882788181303, 'epoch': 0.05}\n",
+            "100% 20/20 [00:24<00:00,  1.24s/it]\n",
+            "[2024-01-27 22:08:39,580] [INFO] [axolotl.train.log:61] [PID:2797] [RANK:0] Training Completed!!! Saving pre-trained model to ./qlora-out\u001b[39m\n",
+            "(PeftModelForCausalLM(   (base_model): LoraModel(     (model): LlamaForCausalLM(       (model): LlamaModel(         (embed_tokens): Embedding(32000, 2048)         (layers): ModuleList(           (0-21): 22 x LlamaDecoderLayer(             (self_attn): LlamaSdpaAttention(               (q_proj): lora.Linear4bit(                 (base_layer): Linear4bit(in_features=2048, out_features=2048, bias=False)                 (lora_dropout): ModuleDict(                   (default): Dropout(p=0.05, inplace=False)                 )                 (lora_A): ModuleDict(                   (default): Linear(in_features=2048, out_features=32, bias=False)                 )                 (lora_B): ModuleDict(                   (default): Linear(in_features=32, out_features=2048, bias=False)                 )                 (lora_embedding_A): ParameterDict()                 (lora_embedding_B): ParameterDict()               )               (k_proj): lora.Linear4bit(                 (base_layer): Linear4bit(in_features=2048, out_features=256, bias=False)                 (lora_dropout): ModuleDict(                   (default): Dropout(p=0.05, inplace=False)                 )                 (lora_A): ModuleDict(                   (default): Linear(in_features=2048, out_features=32, bias=False)                 )                 (lora_B): ModuleDict(                   (default): Linear(in_features=32, out_features=256, bias=False)                 )                 (lora_embedding_A): ParameterDict()                 (lora_embedding_B): ParameterDict()               )               (v_proj): lora.Linear4bit(                 (base_layer): Linear4bit(in_features=2048, out_features=256, bias=False)                 (lora_dropout): ModuleDict(                   (default): Dropout(p=0.05, inplace=False)                 )                 (lora_A): ModuleDict(                   (default): Linear(in_features=2048, out_features=32, bias=False)                 )                 (lora_B): ModuleDict(                   (default): Linear(in_features=32, out_features=256, bias=False)                 )                 (lora_embedding_A): ParameterDict()                 (lora_embedding_B): ParameterDict()               )               (o_proj): lora.Linear4bit(                 (base_layer): Linear4bit(in_features=2048, out_features=2048, bias=False)                 (lora_dropout): ModuleDict(                   (default): Dropout(p=0.05, inplace=False)                 )                 (lora_A): ModuleDict(                   (default): Linear(in_features=2048, out_features=32, bias=False)                 )                 (lora_B): ModuleDict(                   (default): Linear(in_features=32, out_features=2048, bias=False)                 )                 (lora_embedding_A): ParameterDict()                 (lora_embedding_B): ParameterDict()               )               (rotary_emb): LlamaRotaryEmbedding()             )             (mlp): LlamaMLP(               (gate_proj): lora.Linear4bit(                 (base_layer): Linear4bit(in_features=2048, out_features=5632, bias=False)                 (lora_dropout): ModuleDict(                   (default): Dropout(p=0.05, inplace=False)                 )                 (lora_A): ModuleDict(                   (default): Linear(in_features=2048, out_features=32, bias=False)                 )                 (lora_B): ModuleDict(                   (default): Linear(in_features=32, out_features=5632, bias=False)                 )                 (lora_embedding_A): ParameterDict()                 (lora_embedding_B): ParameterDict()               )               (up_proj): lora.Linear4bit(                 (base_layer): Linear4bit(in_features=2048, out_features=5632, bias=False)                 (lora_dropout): ModuleDict(                   (default): Dropout(p=0.05, inplace=False)                 )                 (lora_A): ModuleDict(                   (default): Linear(in_features=2048, out_features=32, bias=False)                 )                 (lora_B): ModuleDict(                   (default): Linear(in_features=32, out_features=5632, bias=False)                 )                 (lora_embedding_A): ParameterDict()                 (lora_embedding_B): ParameterDict()               )               (down_proj): lora.Linear4bit(                 (base_layer): Linear4bit(in_features=5632, out_features=2048, bias=False)                 (lora_dropout): ModuleDict(                   (default): Dropout(p=0.05, inplace=False)                 )                 (lora_A): ModuleDict(                   (default): Linear(in_features=5632, out_features=32, bias=False)                 )                 (lora_B): ModuleDict(                   (default): Linear(in_features=32, out_features=2048, bias=False)                 )                 (lora_embedding_A): ParameterDict()                 (lora_embedding_B): ParameterDict()               )               (act_fn): SiLU()             )             (input_layernorm): LlamaRMSNorm()             (post_attention_layernorm): LlamaRMSNorm()           )         )         (norm): LlamaRMSNorm()       )       (lm_head): Linear(in_features=2048, out_features=32000, bias=False)     )   ) ), LlamaTokenizer(name_or_path='TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T', vocab_size=32000, model_max_length=1000000000000000019884624838656, is_fast=False, padding_side='right', truncation_side='right', special_tokens={'bos_token': '<s>', 'eos_token': '</s>', 'unk_token': '<unk>', 'pad_token': '</s>'}, clean_up_tokenization_spaces=False),  added_tokens_decoder={ \t0: AddedToken(\"<unk>\", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), \t1: AddedToken(\"<s>\", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), \t2: AddedToken(\"</s>\", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), })\n",
+            "\u001b[0m"
+          ]
+        }
+      ],
+      "source": [
+        "!accelerate launch -m axolotl.cli.train config.yaml"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "!python3 -m axolotl.cli.merge_lora config.yaml --lora_model_dir=\"./qlora-out\""
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "5GENnc9Z8v-P",
+        "outputId": "762e6290-9877-485c-c084-5370c3b3d7f3"
+      },
+      "execution_count": 10,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "mkdir: cannot create directory ‘final_model’: File exists\n",
+            "2024-01-27 22:10:36.876247: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n",
+            "2024-01-27 22:10:36.876317: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n",
+            "2024-01-27 22:10:36.878122: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n",
+            "2024-01-27 22:10:38.390922: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT\n",
+            "[2024-01-27 22:10:39,447] [INFO] [datasets.<module>:58] [PID:4079] PyTorch version 2.1.2 available.\n",
+            "[2024-01-27 22:10:39,448] [INFO] [datasets.<module>:95] [PID:4079] TensorFlow version 2.15.0 available.\n",
+            "[2024-01-27 22:10:39,449] [INFO] [datasets.<module>:108] [PID:4079] JAX version 0.4.23 available.\n",
+            "[2024-01-27 22:10:40,350] [INFO] [real_accelerator.py:191:get_accelerator] Setting ds_accelerator to cuda (auto detect)\n",
+            "                                 dP            dP   dP \n",
+            "                                 88            88   88 \n",
+            "      .d8888b. dP.  .dP .d8888b. 88 .d8888b. d8888P 88 \n",
+            "      88'  `88  `8bd8'  88'  `88 88 88'  `88   88   88 \n",
+            "      88.  .88  .d88b.  88.  .88 88 88.  .88   88   88 \n",
+            "      `88888P8 dP'  `dP `88888P' dP `88888P'   dP   dP \n",
+            "                                                       \n",
+            "                                                       \n",
+            "\n",
+            "[2024-01-27 22:10:41,928] [INFO] [axolotl.normalize_config:170] [PID:4079] [RANK:0] GPU memory usage baseline: 0.000GB (+0.255GB misc)\u001b[39m\n",
+            "[2024-01-27 22:10:41,928] [INFO] [axolotl.common.cli.load_model_and_tokenizer:49] [PID:4079] [RANK:0] loading tokenizer... TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T\u001b[39m\n",
+            "[2024-01-27 22:10:42,234] [DEBUG] [axolotl.load_tokenizer:216] [PID:4079] [RANK:0] EOS: 2 / </s>\u001b[39m\n",
+            "[2024-01-27 22:10:42,234] [DEBUG] [axolotl.load_tokenizer:217] [PID:4079] [RANK:0] BOS: 1 / <s>\u001b[39m\n",
+            "[2024-01-27 22:10:42,234] [DEBUG] [axolotl.load_tokenizer:218] [PID:4079] [RANK:0] PAD: 2 / </s>\u001b[39m\n",
+            "[2024-01-27 22:10:42,234] [DEBUG] [axolotl.load_tokenizer:219] [PID:4079] [RANK:0] UNK: 0 / <unk>\u001b[39m\n",
+            "[2024-01-27 22:10:42,235] [INFO] [axolotl.load_tokenizer:230] [PID:4079] [RANK:0] No Chat template selected. Consider adding a chat template for easier inference.\u001b[39m\n",
+            "[2024-01-27 22:10:42,235] [INFO] [axolotl.common.cli.load_model_and_tokenizer:51] [PID:4079] [RANK:0] loading model and (optionally) peft_config...\u001b[39m\n",
+            "[2024-01-27 22:10:42,320] [INFO] [axolotl.load_model:372] [PID:4079] [RANK:0] patching _expand_mask\u001b[39m\n",
+            "[2024-01-27 22:10:45,770] [INFO] [axolotl.load_model:641] [PID:4079] [RANK:0] GPU memory usage after model load: 2.062GB (+0.087GB cache, +0.352GB misc)\u001b[39m\n",
+            "[2024-01-27 22:10:45,787] [INFO] [axolotl.load_model:685] [PID:4079] [RANK:0] converting modules to torch.float16 for flash attention\u001b[39m\n",
+            "[2024-01-27 22:10:45,791] [INFO] [axolotl.load_lora:797] [PID:4079] [RANK:0] found linear modules: ['q_proj', 'down_proj', 'v_proj', 'gate_proj', 'k_proj', 'up_proj', 'o_proj']\u001b[39m\n",
+            "[2024-01-27 22:10:45,791] [DEBUG] [axolotl.load_lora:816] [PID:4079] [RANK:0] Loading pretained PEFT - LoRA\u001b[39m\n",
+            "trainable params: 25,231,360 || all params: 1,125,279,744 || trainable%: 2.2422299996542017\n",
+            "[2024-01-27 22:10:46,372] [INFO] [axolotl.load_model:722] [PID:4079] [RANK:0] GPU memory usage after adapters: 2.590GB (+1.060GB cache, +0.368GB misc)\u001b[39m\n",
+            "[2024-01-27 22:10:46,372] [INFO] [axolotl.scripts.do_merge_lora:79] [PID:4079] [RANK:0] running merge of LoRA with base model\u001b[39m\n",
+            "Unloading and merging model: 100% 468/468 [00:00<00:00, 4211.50it/s]\n",
+            "[2024-01-27 22:10:46,490] [INFO] [axolotl.scripts.do_merge_lora:88] [PID:4079] [RANK:0] saving merged model to: qlora-out/merged\u001b[39m\n",
+            "\u001b[0m"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "from huggingface_hub import HfApi\n",
+        "from google.colab import userdata\n",
+        "\n",
+        "new_model = \"mlabonne/TinyAlpaca\"\n",
+        "\n",
+        "# HF_TOKEN defined in the secrets tab in Google Colab\n",
+        "api = HfApi()\n",
+        "\n",
+        "# Upload merge folder\n",
+        "api.create_repo(\n",
+        "    repo_id=new_model,\n",
+        "    repo_type=\"model\",\n",
+        "    exist_ok=True,\n",
+        ")\n",
+        "api.upload_folder(\n",
+        "    repo_id=new_model,\n",
+        "    folder_path=\"qlora-out/merged\",\n",
+        ")"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 149,
+          "referenced_widgets": [
+            "76eab4e675b34a5486f28d16183658b6",
+            "af7f38e810a64e5f98dd3f33672b8d57",
+            "0e196628e7e64879bcc7184f67404127",
+            "2ee0d001c05a4b89ab7a3cbea71c5960",
+            "8a59f96ead334ba8b6848321fbde0811",
+            "3db6a3ae89ec483783f97d77aef5e5a7",
+            "f589d24de591428cb878405d1eb6034d",
+            "e4520b22ca934c1fbe399131c021d0e8",
+            "cb663cc62fc94108855d9b5509b573d8",
+            "9926acc37862427d9fdd1ef37474d0c9",
+            "215f84842ac5451a8f868e0dc3090a71",
+            "0878f651a6b64ef495ebd5a2a9084b63",
+            "eec99342bca04c1697ec43bc099c22c9",
+            "cb7cc89f3edf4c6c8e38043ef0d697ba",
+            "7a9497ed06004a82b2893e0f5ab03736",
+            "f50ea1d3c5874926a6db2af3d9d795ab",
+            "7851c929f5f64e31856d3793b963130e",
+            "49f8123c3c5e43ababed7e09e97cb7d2",
+            "c4dfec3f687241d6a69cf30252ada077",
+            "a1c9ecf2bc124658a08f585b1bf309e6",
+            "101d0b228b1943ff9c9d69fd6f4847ee",
+            "b03c7fa74c774a39946636803e086218",
+            "90726b0049c344c19fb5c9ef1dcf0628",
+            "bebef38ee9e24586a7f894ffaf1ae43e",
+            "9d90c5ea423e4586bc3bb303bcaa4b03",
+            "d417d5bf00294e3f9cb7e78b5d83ee03",
+            "68eac408135d4d048de89fa674b701da",
+            "34c11d3b1a3441bf8533f7a6f057d0cf",
+            "6270a81b7f5749d7a656c1edaaa63118",
+            "e1de7a96086c4351bba99bbd4d905802",
+            "6d28893d0a054d6aa2726ee94ee0d880",
+            "91c9822b8ef14074bd360bb5d2998267",
+            "8673edee8ab5430588daba8d422999eb"
+          ]
+        },
+        "id": "NsvZw3B7-gfm",
+        "outputId": "68c10dec-ee7a-4c0d-dd8d-c6631b53f4b3"
+      },
+      "execution_count": 13,
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "pytorch_model.bin:   0%|          | 0.00/2.20G [00:00<?, ?B/s]"
+            ],
+            "application/vnd.jupyter.widget-view+json": {
+              "version_major": 2,
+              "version_minor": 0,
+              "model_id": "76eab4e675b34a5486f28d16183658b6"
+            }
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "Upload 2 LFS files:   0%|          | 0/2 [00:00<?, ?it/s]"
+            ],
+            "application/vnd.jupyter.widget-view+json": {
+              "version_major": 2,
+              "version_minor": 0,
+              "model_id": "0878f651a6b64ef495ebd5a2a9084b63"
+            }
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "tokenizer.model:   0%|          | 0.00/500k [00:00<?, ?B/s]"
+            ],
+            "application/vnd.jupyter.widget-view+json": {
+              "version_major": 2,
+              "version_minor": 0,
+              "model_id": "90726b0049c344c19fb5c9ef1dcf0628"
+            }
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "CommitInfo(commit_url='https://huggingface.co/mlabonne/TinyAlpaca/commit/0428c0eb7a6c18dfb7ce7a4cd86ecf4e397048f9', commit_message='Upload folder using huggingface_hub', commit_description='', oid='0428c0eb7a6c18dfb7ce7a4cd86ecf4e397048f9', pr_url=None, pr_revision=None, pr_num=None)"
+            ],
+            "application/vnd.google.colaboratory.intrinsic+json": {
+              "type": "string"
+            }
+          },
+          "metadata": {},
+          "execution_count": 13
+        }
+      ]
+    }
+  ],
+  "metadata": {
+    "accelerator": "GPU",
+    "colab": {
+      "provenance": [],
+      "gpuType": "T4",
+      "include_colab_link": true
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    },
+    "language_info": {
+      "name": "python"
+    },
+    "widgets": {
+      "application/vnd.jupyter.widget-state+json": {
+        "76eab4e675b34a5486f28d16183658b6": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HBoxModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HBoxModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HBoxView",
+            "box_style": "",
+            "children": [
+              "IPY_MODEL_af7f38e810a64e5f98dd3f33672b8d57",
+              "IPY_MODEL_0e196628e7e64879bcc7184f67404127",
+              "IPY_MODEL_2ee0d001c05a4b89ab7a3cbea71c5960"
+            ],
+            "layout": "IPY_MODEL_8a59f96ead334ba8b6848321fbde0811"
+          }
+        },
+        "af7f38e810a64e5f98dd3f33672b8d57": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HTMLModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HTMLModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HTMLView",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_3db6a3ae89ec483783f97d77aef5e5a7",
+            "placeholder": "​",
+            "style": "IPY_MODEL_f589d24de591428cb878405d1eb6034d",
+            "value": "pytorch_model.bin: 100%"
+          }
+        },
+        "0e196628e7e64879bcc7184f67404127": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "FloatProgressModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "FloatProgressModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "ProgressView",
+            "bar_style": "success",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_e4520b22ca934c1fbe399131c021d0e8",
+            "max": 2200164718,
+            "min": 0,
+            "orientation": "horizontal",
+            "style": "IPY_MODEL_cb663cc62fc94108855d9b5509b573d8",
+            "value": 2200164718
+          }
+        },
+        "2ee0d001c05a4b89ab7a3cbea71c5960": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HTMLModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HTMLModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HTMLView",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_9926acc37862427d9fdd1ef37474d0c9",
+            "placeholder": "​",
+            "style": "IPY_MODEL_215f84842ac5451a8f868e0dc3090a71",
+            "value": " 2.20G/2.20G [01:14&lt;00:00, 34.5MB/s]"
+          }
+        },
+        "8a59f96ead334ba8b6848321fbde0811": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": null,
+            "bottom": null,
+            "display": null,
+            "flex": null,
+            "flex_flow": null,
+            "grid_area": null,
+            "grid_auto_columns": null,
+            "grid_auto_flow": null,
+            "grid_auto_rows": null,
+            "grid_column": null,
+            "grid_gap": null,
+            "grid_row": null,
+            "grid_template_areas": null,
+            "grid_template_columns": null,
+            "grid_template_rows": null,
+            "height": null,
+            "justify_content": null,
+            "justify_items": null,
+            "left": null,
+            "margin": null,
+            "max_height": null,
+            "max_width": null,
+            "min_height": null,
+            "min_width": null,
+            "object_fit": null,
+            "object_position": null,
+            "order": null,
+            "overflow": null,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "3db6a3ae89ec483783f97d77aef5e5a7": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": null,
+            "bottom": null,
+            "display": null,
+            "flex": null,
+            "flex_flow": null,
+            "grid_area": null,
+            "grid_auto_columns": null,
+            "grid_auto_flow": null,
+            "grid_auto_rows": null,
+            "grid_column": null,
+            "grid_gap": null,
+            "grid_row": null,
+            "grid_template_areas": null,
+            "grid_template_columns": null,
+            "grid_template_rows": null,
+            "height": null,
+            "justify_content": null,
+            "justify_items": null,
+            "left": null,
+            "margin": null,
+            "max_height": null,
+            "max_width": null,
+            "min_height": null,
+            "min_width": null,
+            "object_fit": null,
+            "object_position": null,
+            "order": null,
+            "overflow": null,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "f589d24de591428cb878405d1eb6034d": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "DescriptionStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "description_width": ""
+          }
+        },
+        "e4520b22ca934c1fbe399131c021d0e8": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": null,
+            "bottom": null,
+            "display": null,
+            "flex": null,
+            "flex_flow": null,
+            "grid_area": null,
+            "grid_auto_columns": null,
+            "grid_auto_flow": null,
+            "grid_auto_rows": null,
+            "grid_column": null,
+            "grid_gap": null,
+            "grid_row": null,
+            "grid_template_areas": null,
+            "grid_template_columns": null,
+            "grid_template_rows": null,
+            "height": null,
+            "justify_content": null,
+            "justify_items": null,
+            "left": null,
+            "margin": null,
+            "max_height": null,
+            "max_width": null,
+            "min_height": null,
+            "min_width": null,
+            "object_fit": null,
+            "object_position": null,
+            "order": null,
+            "overflow": null,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "cb663cc62fc94108855d9b5509b573d8": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "ProgressStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "ProgressStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "bar_color": null,
+            "description_width": ""
+          }
+        },
+        "9926acc37862427d9fdd1ef37474d0c9": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": null,
+            "bottom": null,
+            "display": null,
+            "flex": null,
+            "flex_flow": null,
+            "grid_area": null,
+            "grid_auto_columns": null,
+            "grid_auto_flow": null,
+            "grid_auto_rows": null,
+            "grid_column": null,
+            "grid_gap": null,
+            "grid_row": null,
+            "grid_template_areas": null,
+            "grid_template_columns": null,
+            "grid_template_rows": null,
+            "height": null,
+            "justify_content": null,
+            "justify_items": null,
+            "left": null,
+            "margin": null,
+            "max_height": null,
+            "max_width": null,
+            "min_height": null,
+            "min_width": null,
+            "object_fit": null,
+            "object_position": null,
+            "order": null,
+            "overflow": null,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "215f84842ac5451a8f868e0dc3090a71": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "DescriptionStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "description_width": ""
+          }
+        },
+        "0878f651a6b64ef495ebd5a2a9084b63": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HBoxModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HBoxModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HBoxView",
+            "box_style": "",
+            "children": [
+              "IPY_MODEL_eec99342bca04c1697ec43bc099c22c9",
+              "IPY_MODEL_cb7cc89f3edf4c6c8e38043ef0d697ba",
+              "IPY_MODEL_7a9497ed06004a82b2893e0f5ab03736"
+            ],
+            "layout": "IPY_MODEL_f50ea1d3c5874926a6db2af3d9d795ab"
+          }
+        },
+        "eec99342bca04c1697ec43bc099c22c9": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HTMLModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HTMLModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HTMLView",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_7851c929f5f64e31856d3793b963130e",
+            "placeholder": "​",
+            "style": "IPY_MODEL_49f8123c3c5e43ababed7e09e97cb7d2",
+            "value": "Upload 2 LFS files: 100%"
+          }
+        },
+        "cb7cc89f3edf4c6c8e38043ef0d697ba": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "FloatProgressModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "FloatProgressModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "ProgressView",
+            "bar_style": "success",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_c4dfec3f687241d6a69cf30252ada077",
+            "max": 2,
+            "min": 0,
+            "orientation": "horizontal",
+            "style": "IPY_MODEL_a1c9ecf2bc124658a08f585b1bf309e6",
+            "value": 2
+          }
+        },
+        "7a9497ed06004a82b2893e0f5ab03736": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HTMLModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HTMLModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HTMLView",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_101d0b228b1943ff9c9d69fd6f4847ee",
+            "placeholder": "​",
+            "style": "IPY_MODEL_b03c7fa74c774a39946636803e086218",
+            "value": " 2/2 [01:14&lt;00:00, 74.58s/it]"
+          }
+        },
+        "f50ea1d3c5874926a6db2af3d9d795ab": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": null,
+            "bottom": null,
+            "display": null,
+            "flex": null,
+            "flex_flow": null,
+            "grid_area": null,
+            "grid_auto_columns": null,
+            "grid_auto_flow": null,
+            "grid_auto_rows": null,
+            "grid_column": null,
+            "grid_gap": null,
+            "grid_row": null,
+            "grid_template_areas": null,
+            "grid_template_columns": null,
+            "grid_template_rows": null,
+            "height": null,
+            "justify_content": null,
+            "justify_items": null,
+            "left": null,
+            "margin": null,
+            "max_height": null,
+            "max_width": null,
+            "min_height": null,
+            "min_width": null,
+            "object_fit": null,
+            "object_position": null,
+            "order": null,
+            "overflow": null,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "7851c929f5f64e31856d3793b963130e": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": null,
+            "bottom": null,
+            "display": null,
+            "flex": null,
+            "flex_flow": null,
+            "grid_area": null,
+            "grid_auto_columns": null,
+            "grid_auto_flow": null,
+            "grid_auto_rows": null,
+            "grid_column": null,
+            "grid_gap": null,
+            "grid_row": null,
+            "grid_template_areas": null,
+            "grid_template_columns": null,
+            "grid_template_rows": null,
+            "height": null,
+            "justify_content": null,
+            "justify_items": null,
+            "left": null,
+            "margin": null,
+            "max_height": null,
+            "max_width": null,
+            "min_height": null,
+            "min_width": null,
+            "object_fit": null,
+            "object_position": null,
+            "order": null,
+            "overflow": null,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "49f8123c3c5e43ababed7e09e97cb7d2": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "DescriptionStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "description_width": ""
+          }
+        },
+        "c4dfec3f687241d6a69cf30252ada077": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": null,
+            "bottom": null,
+            "display": null,
+            "flex": null,
+            "flex_flow": null,
+            "grid_area": null,
+            "grid_auto_columns": null,
+            "grid_auto_flow": null,
+            "grid_auto_rows": null,
+            "grid_column": null,
+            "grid_gap": null,
+            "grid_row": null,
+            "grid_template_areas": null,
+            "grid_template_columns": null,
+            "grid_template_rows": null,
+            "height": null,
+            "justify_content": null,
+            "justify_items": null,
+            "left": null,
+            "margin": null,
+            "max_height": null,
+            "max_width": null,
+            "min_height": null,
+            "min_width": null,
+            "object_fit": null,
+            "object_position": null,
+            "order": null,
+            "overflow": null,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "a1c9ecf2bc124658a08f585b1bf309e6": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "ProgressStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "ProgressStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "bar_color": null,
+            "description_width": ""
+          }
+        },
+        "101d0b228b1943ff9c9d69fd6f4847ee": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": null,
+            "bottom": null,
+            "display": null,
+            "flex": null,
+            "flex_flow": null,
+            "grid_area": null,
+            "grid_auto_columns": null,
+            "grid_auto_flow": null,
+            "grid_auto_rows": null,
+            "grid_column": null,
+            "grid_gap": null,
+            "grid_row": null,
+            "grid_template_areas": null,
+            "grid_template_columns": null,
+            "grid_template_rows": null,
+            "height": null,
+            "justify_content": null,
+            "justify_items": null,
+            "left": null,
+            "margin": null,
+            "max_height": null,
+            "max_width": null,
+            "min_height": null,
+            "min_width": null,
+            "object_fit": null,
+            "object_position": null,
+            "order": null,
+            "overflow": null,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "b03c7fa74c774a39946636803e086218": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "DescriptionStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "description_width": ""
+          }
+        },
+        "90726b0049c344c19fb5c9ef1dcf0628": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HBoxModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HBoxModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HBoxView",
+            "box_style": "",
+            "children": [
+              "IPY_MODEL_bebef38ee9e24586a7f894ffaf1ae43e",
+              "IPY_MODEL_9d90c5ea423e4586bc3bb303bcaa4b03",
+              "IPY_MODEL_d417d5bf00294e3f9cb7e78b5d83ee03"
+            ],
+            "layout": "IPY_MODEL_68eac408135d4d048de89fa674b701da"
+          }
+        },
+        "bebef38ee9e24586a7f894ffaf1ae43e": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HTMLModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HTMLModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HTMLView",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_34c11d3b1a3441bf8533f7a6f057d0cf",
+            "placeholder": "​",
+            "style": "IPY_MODEL_6270a81b7f5749d7a656c1edaaa63118",
+            "value": "tokenizer.model: 100%"
+          }
+        },
+        "9d90c5ea423e4586bc3bb303bcaa4b03": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "FloatProgressModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "FloatProgressModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "ProgressView",
+            "bar_style": "success",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_e1de7a96086c4351bba99bbd4d905802",
+            "max": 499723,
+            "min": 0,
+            "orientation": "horizontal",
+            "style": "IPY_MODEL_6d28893d0a054d6aa2726ee94ee0d880",
+            "value": 499723
+          }
+        },
+        "d417d5bf00294e3f9cb7e78b5d83ee03": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HTMLModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HTMLModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HTMLView",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_91c9822b8ef14074bd360bb5d2998267",
+            "placeholder": "​",
+            "style": "IPY_MODEL_8673edee8ab5430588daba8d422999eb",
+            "value": " 500k/500k [00:00&lt;00:00, 48.1kB/s]"
+          }
+        },
+        "68eac408135d4d048de89fa674b701da": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": null,
+            "bottom": null,
+            "display": null,
+            "flex": null,
+            "flex_flow": null,
+            "grid_area": null,
+            "grid_auto_columns": null,
+            "grid_auto_flow": null,
+            "grid_auto_rows": null,
+            "grid_column": null,
+            "grid_gap": null,
+            "grid_row": null,
+            "grid_template_areas": null,
+            "grid_template_columns": null,
+            "grid_template_rows": null,
+            "height": null,
+            "justify_content": null,
+            "justify_items": null,
+            "left": null,
+            "margin": null,
+            "max_height": null,
+            "max_width": null,
+            "min_height": null,
+            "min_width": null,
+            "object_fit": null,
+            "object_position": null,
+            "order": null,
+            "overflow": null,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "34c11d3b1a3441bf8533f7a6f057d0cf": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": null,
+            "bottom": null,
+            "display": null,
+            "flex": null,
+            "flex_flow": null,
+            "grid_area": null,
+            "grid_auto_columns": null,
+            "grid_auto_flow": null,
+            "grid_auto_rows": null,
+            "grid_column": null,
+            "grid_gap": null,
+            "grid_row": null,
+            "grid_template_areas": null,
+            "grid_template_columns": null,
+            "grid_template_rows": null,
+            "height": null,
+            "justify_content": null,
+            "justify_items": null,
+            "left": null,
+            "margin": null,
+            "max_height": null,
+            "max_width": null,
+            "min_height": null,
+            "min_width": null,
+            "object_fit": null,
+            "object_position": null,
+            "order": null,
+            "overflow": null,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "6270a81b7f5749d7a656c1edaaa63118": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "DescriptionStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "description_width": ""
+          }
+        },
+        "e1de7a96086c4351bba99bbd4d905802": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": null,
+            "bottom": null,
+            "display": null,
+            "flex": null,
+            "flex_flow": null,
+            "grid_area": null,
+            "grid_auto_columns": null,
+            "grid_auto_flow": null,
+            "grid_auto_rows": null,
+            "grid_column": null,
+            "grid_gap": null,
+            "grid_row": null,
+            "grid_template_areas": null,
+            "grid_template_columns": null,
+            "grid_template_rows": null,
+            "height": null,
+            "justify_content": null,
+            "justify_items": null,
+            "left": null,
+            "margin": null,
+            "max_height": null,
+            "max_width": null,
+            "min_height": null,
+            "min_width": null,
+            "object_fit": null,
+            "object_position": null,
+            "order": null,
+            "overflow": null,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "6d28893d0a054d6aa2726ee94ee0d880": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "ProgressStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "ProgressStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "bar_color": null,
+            "description_width": ""
+          }
+        },
+        "91c9822b8ef14074bd360bb5d2998267": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": null,
+            "bottom": null,
+            "display": null,
+            "flex": null,
+            "flex_flow": null,
+            "grid_area": null,
+            "grid_auto_columns": null,
+            "grid_auto_flow": null,
+            "grid_auto_rows": null,
+            "grid_column": null,
+            "grid_gap": null,
+            "grid_row": null,
+            "grid_template_areas": null,
+            "grid_template_columns": null,
+            "grid_template_rows": null,
+            "height": null,
+            "justify_content": null,
+            "justify_items": null,
+            "left": null,
+            "margin": null,
+            "max_height": null,
+            "max_width": null,
+            "min_height": null,
+            "min_width": null,
+            "object_fit": null,
+            "object_position": null,
+            "order": null,
+            "overflow": null,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "8673edee8ab5430588daba8d422999eb": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "DescriptionStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "description_width": ""
+          }
+        }
+      }
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}
\ No newline at end of file